IDT:面向隐私保护的双任务对抗攻击
IDT: Dual-Task Adversarial Attacks for Privacy Protection
AI总结:
本文提出 IDT 方法,通过双任务对抗攻击在保护文本隐私属性的同时保持其原有任务效用,并验证其优于现有生成式隐私保护方法。
摘要:
自然语言处理(NLP)模型可能以不同方式泄露私人信息,包括成员推断、重构或属性推断攻击。敏感信息可能并不显式地出现在文本中,而是隐藏在底层的写作特征里。保护隐私的方法可以包括使用模型内部已被证明无法检测敏感属性的表示,或者——例如在用户可能不信任模型的场景中,这正是本文所关注的情形——在模型能够访问原始文本之前对原始文本进行修改。其目标是重写文本,以防止有人推断出敏感属性(例如作者的性别,或通过写作风格推断其位置),同时保持文本对其原始用途仍然有用(例如产品评论的情感)。少数处理这一问题的工作主要集中在生成式技术上。然而,这些方法通常会生成与原文差异很大的文本,或者面临模式崩溃等问题。本文探索了一种对抗攻击技术的新颖适配方法,通过操纵文本,使其在一个任务(隐私)上欺骗分类器,同时保持为另一个任务(效用)训练的另一个分类器的预测不变。我们提出了 IDT,该方法分析由辅助且可解释的模型做出的预测,以识别哪些 token 对于隐私任务而言是重要的、需要被修改,以及哪些 token 应当为效用任务而保留。我们在适用于不同任务的多个 NLP 数据集上进行了评估。自动评估和人工评估表明,IDT 在保留文本效用的同时,在隐私任务上欺骗分类器方面也优于现有方法。
英文摘要:
Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive information may not be explicit in the text, but hidden in underlying writing characteristics. Methods to protect privacy can involve using representations inside models that are demonstrated not to detect sensitive attributes or -- for instance, in cases where users might not trust a model, the sort of scenario of interest here -- changing the raw text before models can have access to it. The goal is to rewrite text to prevent someone from inferring a sensitive attribute (e.g. the gender of the author, or their location by the writing style) whilst keeping the text useful for its original intention (e.g. the sentiment of a product review). The few works tackling this have focused on generative techniques. However, these often create extensively different texts from the original ones or face problems such as mode collapse. This paper explores a novel adaptation of adversarial attack techniques to manipulate a text to deceive a classifier w.r.t one task (privacy) whilst keeping the predictions of another classifier trained for another task (utility) unchanged. We propose IDT, a method that analyses predictions made by auxiliary and interpretable models to identify which tokens are important to change for the privacy task, and which ones should be kept for the utility task. We evaluate different datasets for NLP suitable for different tasks. Automatic and human evaluations show that IDT retains the utility of text, while also outperforming existing methods when deceiving a classifier w.r.t privacy task.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。